© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4887
    Prev
    Next
    INDEX
    Explanations

    crossover design study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ä¾Ŀæ³ķ追究
    -0.07
    _payload
    -0.06
    outh
    -0.06
    άζ
    -0.06
    kses
    -0.06
    çŁ¥éŁ³
    -0.06
    gens
    -0.06
    classes
    -0.06
    angular
    -0.06
    atica
    -0.06
    POSITIVE LOGITS
    æĮ½æķij
    0.08
    对åĨħ
    0.08
    个人çļĦ
    0.08
    -testing
    0.08
    æ¯ı个åѦçĶŁ
    0.08
    IDO
    0.08
     paired
    0.07
    paired
    0.07
    TestData
    0.07
     Palacio
    0.07
    Activations Density 0.115%

    No Known Activations